Draw an Audio is a research-grade AI system that automatically generates contextually accurate, temporally aligned sound effects from silent videos using multimodal conditioning.
PDF2Audio is an open-source tool that transforms PDF documents into high-quality audio files using AI-powered text extraction, script generation, and text-to-speech synthesis.
SafeEar is an open-source AI framework that detects audio deepfakes by analyzing acoustic features while preserving speaker privacy across multiple languages.
F5-TTS is an open-source, high-performance text-to-speech tool that generates natural, expressive speech using flow matching and diffusion transformer models.
MaskGCT is an open-source, multilingual text-to-speech model that delivers high-fidelity voice synthesis, real-time voice cloning, cross-lingual conversion, and fine-grained prosodic control.
NotebookLlama is an open-source Meta project that automatically converts PDF documents into professionally narrated podcast episodes using LLaMA models and TTS synthesis.
CosyVoice 2.0 is an open-source, high-fidelity streaming text-to-speech model that delivers ultra-low-latency, multilingual, emotionally expressive, and speaker-controllable voice synthesis.
VALL-E is a Microsoft Research text-to-speech model that uses discrete audio codes and in-context learning to synthesize personalized speech from short samples.
Alibaba Cloud's AI assistant that transcribes meetings, audio, video and podcasts in real time, separates speakers, translates and produces structured summaries.